@inproceedings{lee-etal-2020-korean,
title = "{K}orean-Specific Emotion Annotation Procedure Using {N}-Gram-Based Distant Supervision and {K}orean-Specific-Feature-Based Distant Supervision",
author = "Lee, Young-Jun and
Lim, Chae-Gyun and
Choi, Ho-Jin",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.199",
pages = "1603--1610",
abstract = "Detecting emotions from texts is considerably important in an NLP task, but it has the limitation of the scarcity of manually labeled data. To overcome this limitation, many researchers have annotated unlabeled data with certain frequently used annotation procedures. However, most of these studies are focused mainly on English and do not consider the characteristics of the Korean language. In this paper, we present a Korean-specific annotation procedure, which consists of two parts, namely n-gram-based distant supervision and Korean-specific-feature-based distant supervision. We leverage the distant supervision with the n-gram and Korean emotion lexicons. Then, we consider the Korean-specific emotion features. Through experiments, we showed the effectiveness of our procedure by comparing with the KTEA dataset. Additionally, we constructed a large-scale emotion-labeled dataset, Korean Movie Review Emotion (KMRE) Dataset, using our procedure. In order to construct our dataset, we used a large-scale sentiment movie review corpus as the unlabeled dataset. Moreover, we used a Korean emotion lexicon provided by KTEA. We also performed an emotion classification task and a human evaluation on the KMRE dataset.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2020-korean">
<titleInfo>
<title>Korean-Specific Emotion Annotation Procedure Using N-Gram-Based Distant Supervision and Korean-Specific-Feature-Based Distant Supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-Jun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chae-Gyun</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ho-Jin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Detecting emotions from texts is considerably important in an NLP task, but it has the limitation of the scarcity of manually labeled data. To overcome this limitation, many researchers have annotated unlabeled data with certain frequently used annotation procedures. However, most of these studies are focused mainly on English and do not consider the characteristics of the Korean language. In this paper, we present a Korean-specific annotation procedure, which consists of two parts, namely n-gram-based distant supervision and Korean-specific-feature-based distant supervision. We leverage the distant supervision with the n-gram and Korean emotion lexicons. Then, we consider the Korean-specific emotion features. Through experiments, we showed the effectiveness of our procedure by comparing with the KTEA dataset. Additionally, we constructed a large-scale emotion-labeled dataset, Korean Movie Review Emotion (KMRE) Dataset, using our procedure. In order to construct our dataset, we used a large-scale sentiment movie review corpus as the unlabeled dataset. Moreover, we used a Korean emotion lexicon provided by KTEA. We also performed an emotion classification task and a human evaluation on the KMRE dataset.</abstract>
<identifier type="citekey">lee-etal-2020-korean</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.199</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>1603</start>
<end>1610</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Korean-Specific Emotion Annotation Procedure Using N-Gram-Based Distant Supervision and Korean-Specific-Feature-Based Distant Supervision
%A Lee, Young-Jun
%A Lim, Chae-Gyun
%A Choi, Ho-Jin
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F lee-etal-2020-korean
%X Detecting emotions from texts is considerably important in an NLP task, but it has the limitation of the scarcity of manually labeled data. To overcome this limitation, many researchers have annotated unlabeled data with certain frequently used annotation procedures. However, most of these studies are focused mainly on English and do not consider the characteristics of the Korean language. In this paper, we present a Korean-specific annotation procedure, which consists of two parts, namely n-gram-based distant supervision and Korean-specific-feature-based distant supervision. We leverage the distant supervision with the n-gram and Korean emotion lexicons. Then, we consider the Korean-specific emotion features. Through experiments, we showed the effectiveness of our procedure by comparing with the KTEA dataset. Additionally, we constructed a large-scale emotion-labeled dataset, Korean Movie Review Emotion (KMRE) Dataset, using our procedure. In order to construct our dataset, we used a large-scale sentiment movie review corpus as the unlabeled dataset. Moreover, we used a Korean emotion lexicon provided by KTEA. We also performed an emotion classification task and a human evaluation on the KMRE dataset.
%U https://aclanthology.org/2020.lrec-1.199
%P 1603-1610
Markdown (Informal)
[Korean-Specific Emotion Annotation Procedure Using N-Gram-Based Distant Supervision and Korean-Specific-Feature-Based Distant Supervision](https://aclanthology.org/2020.lrec-1.199) (Lee et al., LREC 2020)
ACL